718d50d6d0
Minor tweak to #114101 - as we're reducing the instruction count, we should prefer the fold if the old/new costs are the same.
54 lines
3.5 KiB
LLVM
54 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64 -O3 -S < %s | FileCheck %s --check-prefixes=SSE,SSE2
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v2 -O3 -S < %s | FileCheck %s --check-prefixes=SSE,SSE4
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=btver2 -O3 -S < %s | FileCheck %s --check-prefixes=AVX,AVX1
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v3 -O3 -S < %s | FileCheck %s --check-prefixes=AVX,AVX2
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=SSE,SSE2
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v2 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=SSE,SSE4
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=btver2 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=AVX,AVX1
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v3 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=AVX,AVX2
|
|
|
|
define <4 x double> @PR94546(<4 x double> %a, <4 x double> %b) {
|
|
; SSE2-LABEL: @PR94546(
|
|
; SSE2-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <2 x i32> <i32 0, i32 6>
|
|
; SSE2-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <2 x i32> <i32 1, i32 7>
|
|
; SSE2-NEXT: [[TMP3:%.*]] = fadd <2 x double> [[TMP1]], [[TMP2]]
|
|
; SSE2-NEXT: [[TMP4:%.*]] = shufflevector <2 x double> [[TMP3]], <2 x double> poison, <4 x i32> <i32 0, i32 poison, i32 poison, i32 1>
|
|
; SSE2-NEXT: ret <4 x double> [[TMP4]]
|
|
;
|
|
; SSE4-LABEL: @PR94546(
|
|
; SSE4-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 poison, i32 poison, i32 6>
|
|
; SSE4-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 poison, i32 poison, i32 7>
|
|
; SSE4-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
|
|
; SSE4-NEXT: ret <4 x double> [[TMP3]]
|
|
;
|
|
; AVX-LABEL: @PR94546(
|
|
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 poison, i32 poison, i32 6>
|
|
; AVX-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 poison, i32 poison, i32 7>
|
|
; AVX-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
|
|
; AVX-NEXT: ret <4 x double> [[TMP3]]
|
|
;
|
|
%vecext = extractelement <4 x double> %a, i32 0
|
|
%vecext1 = extractelement <4 x double> %a, i32 1
|
|
%add = fadd double %vecext, %vecext1
|
|
%vecinit = insertelement <4 x double> poison, double %add, i32 0
|
|
%vecext2 = extractelement <4 x double> %a, i32 2
|
|
%vecext3 = extractelement <4 x double> %a, i32 3
|
|
%add4 = fadd double %vecext2, %vecext3
|
|
%vecinit5 = insertelement <4 x double> %vecinit, double %add4, i32 1
|
|
%vecext6 = extractelement <4 x double> %b, i32 0
|
|
%vecext7 = extractelement <4 x double> %b, i32 1
|
|
%add8 = fadd double %vecext6, %vecext7
|
|
%vecinit9 = insertelement <4 x double> %vecinit5, double %add8, i32 2
|
|
%vecext10 = extractelement <4 x double> %b, i32 2
|
|
%vecext11 = extractelement <4 x double> %b, i32 3
|
|
%add12 = fadd double %vecext10, %vecext11
|
|
%vecinit13 = insertelement <4 x double> %vecinit9, double %add12, i32 3
|
|
%shuffle = shufflevector <4 x double> %vecinit13, <4 x double> %a, <4 x i32> <i32 0, i32 poison, i32 poison, i32 3>
|
|
ret <4 x double> %shuffle
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; AVX1: {{.*}}
|
|
; AVX2: {{.*}}
|
|
; SSE: {{.*}}
|